|
--- |
|
license: apache-2.0 |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- precision |
|
- recall |
|
- f1 |
|
- accuracy |
|
model-index: |
|
- name: testlink-class-2 |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# testlink-class-2 |
|
|
|
This model is a fine-tuned version of [PlanTL-GOB-ES/bsc-bio-ehr-es-pharmaconer](https://huggingface.co/PlanTL-GOB-ES/bsc-bio-ehr-es-pharmaconer) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.1878 |
|
- Precision: 0.7 |
|
- Recall: 0.6959 |
|
- F1: 0.6979 |
|
- Accuracy: 0.9758 |
|
|
|
## Model description |
|
|
|
More information needed |
|
|
|
## Intended uses & limitations |
|
|
|
More information needed |
|
|
|
## Training and evaluation data |
|
|
|
More information needed |
|
|
|
## Training procedure |
|
|
|
### Training hyperparameters |
|
|
|
The following hyperparameters were used during training: |
|
- learning_rate: 5e-05 |
|
- train_batch_size: 32 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 30 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:| |
|
| No log | 1.0 | 29 | 0.1455 | 0.7025 | 0.6491 | 0.6748 | 0.9758 | |
|
| No log | 2.0 | 58 | 0.1404 | 0.6845 | 0.6725 | 0.6785 | 0.9748 | |
|
| No log | 3.0 | 87 | 0.1511 | 0.6384 | 0.6608 | 0.6494 | 0.9730 | |
|
| No log | 4.0 | 116 | 0.1515 | 0.6353 | 0.6316 | 0.6334 | 0.9723 | |
|
| No log | 5.0 | 145 | 0.1563 | 0.6 | 0.7193 | 0.6543 | 0.9714 | |
|
| No log | 6.0 | 174 | 0.1820 | 0.6772 | 0.6257 | 0.6505 | 0.9734 | |
|
| No log | 7.0 | 203 | 0.1671 | 0.565 | 0.6608 | 0.6092 | 0.9695 | |
|
| No log | 8.0 | 232 | 0.1664 | 0.6592 | 0.6901 | 0.6743 | 0.9743 | |
|
| No log | 9.0 | 261 | 0.1726 | 0.6725 | 0.6725 | 0.6725 | 0.9754 | |
|
| No log | 10.0 | 290 | 0.1929 | 0.6328 | 0.6550 | 0.6437 | 0.9714 | |
|
| No log | 11.0 | 319 | 0.1749 | 0.6894 | 0.6491 | 0.6687 | 0.9737 | |
|
| No log | 12.0 | 348 | 0.1675 | 0.6889 | 0.7251 | 0.7066 | 0.9745 | |
|
| No log | 13.0 | 377 | 0.1806 | 0.6186 | 0.7018 | 0.6575 | 0.9723 | |
|
| No log | 14.0 | 406 | 0.1732 | 0.6193 | 0.7135 | 0.6630 | 0.9723 | |
|
| No log | 15.0 | 435 | 0.1837 | 0.6080 | 0.7076 | 0.6541 | 0.9714 | |
|
| No log | 16.0 | 464 | 0.1774 | 0.6798 | 0.7076 | 0.6934 | 0.9750 | |
|
| No log | 17.0 | 493 | 0.1700 | 0.6477 | 0.7310 | 0.6868 | 0.9737 | |
|
| 0.0031 | 18.0 | 522 | 0.1719 | 0.6219 | 0.7310 | 0.6720 | 0.9732 | |
|
| 0.0031 | 19.0 | 551 | 0.1749 | 0.6440 | 0.7193 | 0.6796 | 0.9743 | |
|
| 0.0031 | 20.0 | 580 | 0.1808 | 0.7278 | 0.6725 | 0.6991 | 0.9761 | |
|
| 0.0031 | 21.0 | 609 | 0.1753 | 0.6595 | 0.7135 | 0.6854 | 0.9737 | |
|
| 0.0031 | 22.0 | 638 | 0.1816 | 0.6489 | 0.7135 | 0.6797 | 0.9739 | |
|
| 0.0031 | 23.0 | 667 | 0.1835 | 0.6839 | 0.6959 | 0.6899 | 0.9752 | |
|
| 0.0031 | 24.0 | 696 | 0.1864 | 0.7134 | 0.6842 | 0.6985 | 0.9759 | |
|
| 0.0031 | 25.0 | 725 | 0.1919 | 0.7516 | 0.6725 | 0.7099 | 0.9765 | |
|
| 0.0031 | 26.0 | 754 | 0.1823 | 0.6758 | 0.7193 | 0.6969 | 0.9743 | |
|
| 0.0031 | 27.0 | 783 | 0.1822 | 0.6721 | 0.7193 | 0.6949 | 0.9741 | |
|
| 0.0031 | 28.0 | 812 | 0.1862 | 0.7083 | 0.6959 | 0.7021 | 0.9759 | |
|
| 0.0031 | 29.0 | 841 | 0.1879 | 0.7 | 0.6959 | 0.6979 | 0.9758 | |
|
| 0.0031 | 30.0 | 870 | 0.1878 | 0.7 | 0.6959 | 0.6979 | 0.9758 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.28.1 |
|
- Pytorch 2.0.0+cu118 |
|
- Datasets 2.12.0 |
|
- Tokenizers 0.13.3 |
|
|
